{ "vocab_size": 129280, "dim": 1024, "moe_inter_dim": 384, "n_layers": 15, "n_hash_layers": 1, "n_mtp_layers": 0, "n_heads": 16, "n_routed_experts": 32, "n_shared_experts": 1, "n_activated_experts": 6, "score_func": "sqrtsoftplus", "route_scale": 2.436, "swiglu_limit": 10.0, "q_lora_rank": 256, "head_dim": 256, "rope_head_dim": 64, "o_groups": 2, "o_lora_rank": 1024, "window_size": 128, "original_seq_len": 0, "rope_theta": 10000, "rope_factor": 1, "beta_fast": 32, "beta_slow": 1, "index_n_heads": 64, "index_head_dim": 128, "index_topk": 1024, "hc_mult": 4, "hc_sinkhorn_iters": 20, "dtype": "bf16", "compress_rope_theta": 160000, "compress_ratios": [ 0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4 ] }